Backlog

Next up

In Progress

Done

Main Roadmap

When you use Google Drive as a team, you usually store data in “Shared” drives rather than in your personal drive (using precious personal space). Currently Chipp can only add sources that exist in the user’s personal drive. We want to add dynamic Chipp sources to a Google “Shared Drive” that multiple users can manage, and have Chipp use all resources in that folder. This is a blocker for our finance-bot projects where resources and access are internal. TL:DR; Please add the ability to add resources from a Google “Shared drive”, different from a shared folder, with the ability to import either a folder or a file.

In Review

Please add Shared Drives (not just personal) for Google Drive as Sources

Matthew Lee

Hello, I want to request two features. First one is PDF dynamic watermarking where there should be option to choose dynamic watermark like name and email address of that account or name of the AI tool etc. the second feature request is payment methods for people from India because here we don’t have stripe. Thank you.

PDF dynamic watermark and Payment method for Indian people

Amol Shinde

<h2 id="overview">Overview</h2>
Feature request from Featurebase to enable programmatic agent creation and interaction via API, allowing external systems to spin up and use Chipp agents without the UI.
<h2 id="subissues">Sub-Issues</h2>
<ul>
<li>ENG-1608: Template-Based Agent Creation Endpoint (POST /templates/{id}/instantiate)</li>
<li>ENG-1609: Simple Input API for Template-Based Agents (POST /agents/{id}/input)</li>
<li>ENG-1610: Optional Webhook Delivery for Longer Tasks</li>
</ul>
<h2 id="usecases">Use Cases</h2>
<ol>
<li>Agencies: Spin up white-labeled agents for clients programmatically</li>
<li>SaaS integrations: Use Chipp agents as backend helpers</li>
<li>Automation flows: Integrate agents into Zapier/Make workflows</li>
<li>Long-running tasks: Async webhook delivery for complex workflows</li>
</ol>
<h2 id="mvpscope">MVP Scope</h2>
<ol>
<li>Mark agents as "templates" in UI</li>
<li>POST /templates/{templateid}/instantiate → returns new agentid + entry points</li>
<li>POST /agents/{agent_id}/input → returns agent response</li>
<li>Optional webhook_url parameter for async delivery</li>
</ol>
<h2 id="technicalconsiderations">Technical Considerations</h2>
<ul>
<li>Authentication: API keys or OAuth</li>
<li>Rate limiting for agent creation</li>
<li>Template versioning</li>
<li>Webhook retry logic</li>
</ul>

Chipp Agent Template API: API endpoints for programmatic agent creation and input

Linear

1 - Add custom voice (maybe Elevenlabs integration). 2 - Voice-based Chip to Chipp conversations. 3 - Voice conversation recordings with downloadable file. 4 - Voice dictation.

Voice Mode Features

Kevin Greene

It would make sense to be able to add data captured during "lead capture" as variables that can be sent sent in the custom API actions

Было бы разумно иметь возможность добавлять данные, полученные во время "захвата лидов", в качестве переменных, которые можно отправлять в пользовательских действиях API.

Добавьте данные о захвате лидов в качестве переменных в пользовательские действия API

Add lead capture data as variables in the custom API actions

Joe Walsh

Unable to access my google sheets (leads management) If I registered with a business, non-google account. It asks for permission to access my own app sheets.

Way to access Google Sheets for non-google emails?

Bookie

In my dashboard it says the allowance coming with my plan would refresh on the 23rd but it didn’t, also the @Auto Top Up doesn't work , so I had to quickly add some credits manually to avoid a service interruption for my customers.

Credit Allowance doesn't refresh

Matthias Werner

I set the Top up amount to $50 and the threshold to 25%. My current credit balance is at $1.78. It seems the auto top up doesn’t work.

Auto Top Up doesn't work

It would be great to have the usage analytics also in a time-series, like token consumption per day within the last X days.Just a simple chart would be enough: x-axis the dates, y-axis token consumption per day. Ideally input and output separated.This would be interesting, for example, when I change knowledge sources or adjust the custom instructions. That way I could see the impact of these changes on the token consumption. But just in general it would interesting to see this over time, to detect peak consumption times or which day of the week the users are mostly active or to understand if the overall usage increases or decreases over time.

Usage Analytics over time

In my app the messages are not streamed anymore (no “typing” effect from the AI), it’s just sent as a complete message. Is this a bug or can I change some settings somewhere? Streamed responses seem to be perceived as nicer UX.

Message streaming seems off

I would be great if an API could be used to set users to “subcribed” or revoke this status, to generally query the user database or to trigger workflows when a new user singed up.

Planned

API features to manage meta data

Would it be possible to add the custom subdomain for your HQ like you do now for the individual Chipps?

Unique subdomain for HQ

Don Barger

I am troubleshooting a Slack integration, and just received the following error: “Token usage limit exceeded. You've used 270,464 of 100,000 tokens this month.”I’ve reviewed my Settings, the app logs, and other areas in Chipp to determine what is causing my requests to have this higher token usage, but I don’t have a clear answer yet.Can the token usage be added to the Chat Logs as an additional, optional column? Or perhaps have a token usage log, if there are other ways tokens might be used per account?Perhaps I would benefit from creating separate apps with more specific purposes to get the usage per request lower. I can’t be sure without more contextual data, though.

Provide token usage details/context

Jen Bauer

Same as Chipp App Slack deployment but for MS Teams

Microsoft Teams Deployment

Lewis Lovelock

If knowledge base files could be DELETEd and POSTed via API, then this would avoid the manual process of navigating to the Chipp website and clicking to delete and upload, doing this for each bot. That would make a massive difference to my use case, given my large number of resource files multiplied by a large number of Chipp apps.

API access to POST and DELETE knowledge base files

Brenton Boswell

<h1>TL;DR: </h1>Please read the browser’s language setting and help us to provide (and present )localized title, description, and conversation starters when they open the chat.<h1>User Story: </h1>A French speaker accesses our website, using the French interface for the site. They find the chat button and open it. They are presented with a chipp bot’s title, description, and starter questions, all in English. The chat agent is capable of speaking with them in French, but unless they “try” asking a question in French, they may leave without getting the response.<h1>Background: </h1>We work across thousands of languages, but our sites and software support 10ish "gateway" languages like French, Arabic, Spanish that people usually have to learn to use their phones or computers. Modern localized websites can read the language or location of the browser to guess what language the person might want to use.Most of our software documentation is in English. The goal for our bots is to harness those to provide "bring your own language" support for software through any the 90+ languages that the models can use. Basically, we want it to support the user in “any” language of wider communication, but we have no way to visually communicate to the user that their language is supported.The agents can seamlessly give responses across those languages, except the user has to know to ask the first question in their language. Please give us a way to let the user know that their language is supported.<h1>User Side</h1><ul><li>Try to read the browser language setting of the user and present the starting interface (title, description, conversation starter questions, starter message) in that language. The content can be generated or developer-provided. For Right-to-Left languages like Arabic and Hebrew, adjust text positioning accordingly.</li><li>Even if the site reads the browser settings, It is still helpful to give a a dropbox where the user can override with a “starting/interface” language, and provide the initial interface in that language.</li></ul><h1>Developer Side</h1>I would love to translate (and use) 3 strings and 4 questions for each language for each agent to present something more accessible on the front page. Once the user asks the first question, the bot can take over and translate content on the fly. We don’t need to translate the bot’s sources.<h2>Options</h2><ul><li>Give the developer the option to define Title, Description and Conversation Starters in a selection of languages. This is the way the Google Play store works.</li><li>For any languages where the dev hasn’t translated the text, generate localzed versions of the content.</li><li>Allow the Dev to pass a language flag to the app based on user/browser settings. (Example: the user has selected already the French interface on our website, so we pass “fr” when loading the widget.) This could be passed as a variable when loading the iframe (either as a variable “lang=fr”, or url “https://keymansupport-10011648.chipp.ai/fr”).</li></ul><h1>Alternate Option Suggested</h1>I only need to translate (and use) title, description and conversation starters to present something more accessible on the agent’s front page. Valentina has suggested duplicating the bots and providing separate copies for each target language. This presents 2 problems: <ul><li>Even 10 monolingual copies of our 50 bots would push us to 500 bots and become nearly impossible to manage updates to every copy. </li><li>With a global audience, we don’t know what language the user will want, though we can pick a few obvious targets, and we don’t want to spend time or resources creating a fully separate bot for a language that may never be used.</li></ul>

Collect and show multilingual Title, description, and conversation starters.

It would be great to be able to GET, DELETE and POST (update) the Prompt for a Chipp chat. If I edit (at my end) master snippets of prompt instructions that are common to many Chipp apps, but then other parts of the prompt vary from app to app, then I can calculate/compile each prompt from its components and send it to Chipp. This would allow the updating and managing of many prompts at once, so that all chats benefit from prompt improvements.

API access to editing System Prompts

I need a many-to-many mapping of users to apps. In the HQ environment you can DUPLICATE apps from one WORKSPACE to another, but I want to instead LINK the same app to multiple HQs, editing it just in MY workspace. (I need apps A, B, C and F accessible to Group 1, and apps B, C and D accessible to Group 2. Can this be done with HQs? Duplication isn't the right approach, because it forks the version, making hand-edits necessary for every clone.)

many-to-many mapping of users to apps!

Hello, Not sure this is a feature request or bug. We cannot change our admin login email in the setting backed. Please advise.

Change email in admin workspace.

Alan

Here’s a crazy idea. Can we add chipp as a browser extension where you can just embed a chipp (or chipp of chipps) right into the browser? If we did this, we could then create new services that people could keep in their browser bar without having to go to a particular website to access the chipp.

Chipp Browser Extension

I have a lot of data in Airtable, I would like to ask questions about it on Chipp

Integrate Chipp with Airtable

Scott Meyer

It would be great if there was a setting to enable automatic transcripts of voice mode conversations. Otherwise, everything is gone after closing the conversation and the feature has limited value.

Transcript of voice mode conversations

Implement Model Context Prototcol to enable models and assistants to securely access external data sources, tools, and prompts through a standardized client-server architecture

Chipp as MCP Server

Bing Mei

Now with the usage-based pricing, it would be great to have even deeper insight into the credit consumption. E.g. a breakdown by app or even by end-user, number of messages per period, or a usage timeline to identify peaks and spikes.In the long-run it might be cool to also have end-user facing analytics about their own usage, so we could come up with usage-based pricing ourselves.

More Usage & Credit Consumption Analytics

Can you create an easy way to link a chatbot to a Discord channel? In the meantime, can you post the instructions for the not so easy way to link them ;)

Discord and Chatbots

Hi there, in my usage analytics, the per user breakdown doesn’t show data. The users have to sign up for the app.<img data-width="100%" data-align="left" alt="" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/6969fdacd1f420947ed1a865/019bc606-d7d7-7bb1-8c7a-c49601d850f6/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTE2IGF0IDA5LjU3LjIzLnBuZw.png" data-featurebase-content-filename="Screenshot 2026-01-16 at 09.57.23.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/6969fdacd1f420947ed1a865/019bc606-d7d7-7bb1-8c7a-c49601d850f6/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTE2IGF0IDA5LjU3LjIzLnBuZw.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=204f3b900badb3190bc5104cd865e9a82845e396da3b91d24b7c427177aeb70f">

Per User usage data not shown

When inspecting chat histories, much formatting is lost. This makes it impossible to QA end-users’ experiences. Importantly for us, we use models that properly render Maths notation instead of showing the underlying LaTex (which is cumbersome to read). HOWEVER, the chat logs don’t do proper Maths notation. We can’t read the chats properly, and we can’t assess what the original chats actually looked like.

Chat logs need to render the same as the original chat.

Consistent response to the prompt “when should I pick a qms vs plm” <img data-width="100%" data-align="left" alt="" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/697bb1378b28e82082b8222d/019c0b2c-2ba5-7c12-86d5-5d8ddf2a0649/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTI5IGF0IDEuMzkuNTPigK9QTS5wbmc.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/697bb1378b28e82082b8222d/019c0b2c-2ba5-7c12-86d5-5d8ddf2a0649/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTI5IGF0IDEuMzkuNTPigK9QTS5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=b3a1755b5b0206c56bcab8b7db19b30e203b9295a32d3b75093691cf646c859a" data-featurebase-content-filename="Screenshot 2026-01-29 at 1.39.53 PM.png">

"Failed to generate a response"

Troy Michels

Sources used do not load when citing - The name is never loaded, and just an ID appears for the citation, it even looks like it’s perpetually still loading based on the animation on the citation. When you click on the citation, you get a blank modal. <img data-width="100%" data-align="left" alt="" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/697b6b3777d829b9f658c025/019c0a1a-bb61-7935-a2c5-5ee8477137e4/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTI5IGF0IDkuMTIuNDnigK9BTS5wbmc.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/697b6b3777d829b9f658c025/019c0a1a-bb61-7935-a2c5-5ee8477137e4/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTI5IGF0IDkuMTIuNDnigK9BTS5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=bcb7f85df9bbae1167632ba9fc931a0653bd6e72f9663d074155789b7402ddf7" data-featurebase-content-filename="Screenshot 2026-01-29 at 9.12.49 AM.png"><img data-width="100%" data-align="left" alt="" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/697b6b3777d829b9f658c025/019c0a1a-b5e1-7beb-b046-8f4fe5c06289/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTI5IGF0IDkuMTIuNTXigK9BTS5wbmc.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/697b6b3777d829b9f658c025/019c0a1a-b5e1-7beb-b046-8f4fe5c06289/b64u-U2NyZWVuc2hvdCAyMDI2LTAxLTI5IGF0IDkuMTIuNTXigK9BTS5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=36278891dd3764f36ff8f97769ef035528f7d01c7999e73a184f4208aa8a214e" data-featurebase-content-filename="Screenshot 2026-01-29 at 9.12.55 AM.png">

Source do not load

This seems to happen regularly. I’ve mentioned it in discord and it gets fixed, only to break again. All Youtube imports time out. They seem to do the extraction step but time out on transcription.

Youtube imports time out

A Chipp chat should be able to access other Chipps to tap into their knowledge and expertise. Think concierage Chipp wiht a team of virtual Chipps supporting it

Completed

Low Priority

Chipp to Chipp

Talk to your AI agents and get an audio response

Fale com os seus agentes de IA e obtenha uma resposta áudio

Voz Chipp

Chipp Voice

Ability to record all/chosen messages in long-term memory for the AI to remember and learn from past conversations.

User memory feature 🧠

Maaria Tiensivu

Currently if a user starts chatting after the initial session the chat is not capture in chatlog

WhatsApp reengagement needs to go to chatlog

scottdavidmeyer

Suggestion: Add an expand/contract button (for media over 700px) or pop out/pop in button (like Gmail does with emails) that can toggle a widget to nearly fullscreen. Alternately, give a button to “pop out” the chat to a new fullscreen item. It could look something like this on desktop (hacked via CSS):<img data-width="100%" data-align="left" alt="" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/68550e2ca23aa2e89b87ecd1/01978c3e-8d06-7e60-9899-4784125381ae/b64u-aW1hZ2UucG5n.png">The iFrame embed code seems to give the option of defining an internal width, but I don’t see such a custom option for widgets. We could override the default width via CSS, but that is fragile and not dynamic.

Please add a way to toggle a widget to nearly fullscreen

It would be incredibly helpful to have a dictation feature (voice-to-text input) directly within Chipp, similar to how ChatGPT allows users to speak their messages. This is especially useful for:<ul><li>Users who prefer speaking over typing</li><li>Accessibility for differently-abled users</li><li>Faster content creation on mobile</li><li>Enhancing user experience in productivity and creative tasks</li></ul>This feature could significantly reduce friction for users engaging with AI on mobile or during multitasking scenarios. Hope this can be considered for a future update!

Add Dictation (Voice-to-Text) Feature Like in ChatGPT

Kayden Khan

Claude 4

Lucas Retzer

I don’t know why, but this keeps stopping from working. I uploaded my PDF with links as a source, but when I ask in the chat for a meditation, the app gives me a non-existent link. It worked for a while, but now it doesn’t anymore. I also tried it with an Excel sheet, a Google Sheet, and that doesn’t work either. I don’t understand it at all, and I’ve been trying to get this working for a year already. Is this just never going to work? This is my app: https://mediteren.frankbruining.com

No URL retrieving from my documents

frankbruining

Will there be a timeline on when will Gemini 2.5 Flash/Pro be available on Chipp? I’ve had a lot of success performing some large-amount-of-text tasks with the Gemini 2.5 Flash/Pro model, and I’m hoping that it can be on Chipp.

Gemini 2.5 Flash/Pro

David Dai

We recently enabled the Voice Mode and thought it was pretty awesome!<img data-width="100%" data-align="left" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/6914ca9596f09da94d7ccbce/019a7936-32ec-7ab5-828f-b1c14edb3e46/b64u-aW1hZ2UucG5n.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/6914ca9596f09da94d7ccbce/019a7936-32ec-7ab5-828f-b1c14edb3e46/b64u-aW1hZ2UucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=fd3c6f936dacfaa688c5eab7e53d9746f44a53b8963a918547b62fe21cf3cc5a" data-featurebase-content-filename="image.png"> Then it seemed to go away… my manager and I (both expert computer users, with a focus on helping/training users) had trouble finding it. 😕 We discovered it was under the ➕ icon, which made difficult to find: <img data-width="100%" data-align="left" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/6914ca9596f09da94d7ccbce/019a7934-8417-7d7f-ba6f-b0f3b908e043/b64u-MjAyNS0xMS0xMl8wOS0zOS0xNy5QTkc.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/6914ca9596f09da94d7ccbce/019a7934-8417-7d7f-ba6f-b0f3b908e043/b64u-MjAyNS0xMS0xMl8wOS0zOS0xNy5QTkc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=bdb2cc894bb10ca5ab0721a712236d4ae19177eef0a438f16cb7bc80687c78b5" data-featurebase-content-filename="2025-11-12_09-39-17.PNG"> We’re concerned that users will also struggle to find it and I’d like to suggest rearranging the icons so it’s easier to find the various options. Perhaps something like this? <img data-width="100%" data-align="left" data-featurebase-content-key="67fd29a511c8cbaf2c3254ad/post/6914ca9596f09da94d7ccbce/019a7935-7f73-7f85-8cbd-a7f72225852e/b64u-aW1hZ2UucG5n.png" src="https://67fd29a511c8cbaf2c3254ad.featurebase-attachments.com/c/post/6914ca9596f09da94d7ccbce/019a7935-7f73-7f85-8cbd-a7f72225852e/b64u-aW1hZ2UucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260130T030000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260130%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=bfa5b53a0f8710739ac44351fdac63770f50b322bca9dcdd304ccfa94e0b1cce" data-featurebase-content-filename="image.png">Thank you for considering!James Post